AgentMeter

Know what every customer actually costs you.

Capture model calls, agent steps, retries, and non-LLM usage. Attribute cost per customer in real time. React before the bill lands. Bill through Stripe Connect.

5 min SDK installMIT open core
Works with every stackLangGraphCrewAIMastraOpenAI AgentsPydantic AIVercel AI SDK
01Discover.
02Track.
03React.
04Bill.
The product

Not a dashboard.
A cost system that reacts.

Dashboards get checked after damage is done. AgentMeter is built around cost signals that can trigger rules, billing, and customer-facing usage views.
01

Discover

Use the CLI and integration guide to identify LLM providers and declared non-LLM cost sources before production rollout.

Cost Source Checklist
review before go-live
02

Track

Stream tokens, tool calls, agent steps, retries, and configured usage metrics to the same customer-level cost view.

per customer
per step, per model, per run
03

React

Use rules for alerts, budget hard-stops, throttles, model routing, failover, and margin recommendations.

pre-call
SDK-side enforcement
04

Bill

Connect Stripe, generate invoices, and expose usage to end customers through a white-label portal.

Stripe Connect
builder-owned payouts
The wedge

You are blind to
30-60% of your agent cost.

A real agent calls search, speech, vector databases, inference APIs, and workflow tools. AgentMeter tracks configured non-LLM usage next to model calls.

LLM-only view

LLM$0.18
ElevenLabs TTSmissing
Pineconemissing
Serpermissing
Deepgrammissing

actual per-customer cost: unknown

AgentMeter view

LLM$0.18
ElevenLabs TTS$0.13
Pinecone$0.07
Serper$0.05
Deepgram$0.03

acme.co · today · $0.46

React

Rules that run before the call,
not after the bill.

Pre-call rules run in the SDK for budget hard-stops, throttles, model routing, and failover. Post-call rules handle alerts, anomaly detection, and margin diagnosis.
rule budget_limit {  mode  pre-call  when  customer.daily_spend >= 50  then  block with AgentMeterBudgetExceeded}

Blocks runaway spend before the provider call. Events still reconcile back to server truth.

Install

Five minutes to first cost.
Thirty to full pipeline.

One SDK for TypeScript and Python. Track LLM usage automatically through wrappers, then add configured non-LLM usage with reportUsage.
// 1. installpnpm add @agentmeter/sdk// 2. init — auto-patches openai / @anthropic-ai/sdk / aiimport { init, track } from "@agentmeter/sdk";import OpenAI from "openai";init({ apiKey: process.env.AGENTMETER_API_KEY });const openai = new OpenAI();// 3. wrap your agent run with customer + step contextawait track(user.id, { step: "draft" }, async () => {  await openai.chat.completions.create({ ... });});
Bill

A usage portal
under your brand.

Hosted portal links let end customers inspect usage and invoices without seeing anyone else's data.
usage.acme.co

Hi, Morgan

May 2026
You used $47.50 of your $100 monthly budget.13 days left
LLM calls$38.30
ElevenLabs$6.20
Pinecone$3.00
vs. the status quo

One tool
instead of three.

Most teams stitch together provider dashboards, observability tools, and billing scripts. AgentMeter is built for the combined workflow.
AgentMeter feature comparison
Spreadsheet + provider dashboardHelicone / LangfuseBuild in-houseAgentMeter
Automatic LLM cost captureYesYesYesYes
Non-LLM cost trackingNoNoNoYes
Step-level cost per customerNoNoNoYes
Pre-call budget enforcementNoNoYesYes
Model routing per stepNoNoYesYes
Stripe Connect billingNoNoNoYes
White-label customer portalNoNoNoYes
Open core, self-hostableNoYesYesYes
Open core

MIT-licensed. Self-host in one command.

SDKs and core backend are MIT. Run AgentMeter on your own infrastructure when compliance requires it. Enterprise modules in src/ee are source-available under ELv2.

$ your-machine
# clone and run
git clone github.com/SpaceGravity/agentmeter
docker compose up
-> http://localhost:3000

# SDK in your app
pnpm add @agentmeter/sdk
Pricing

Start free.
Pay only when you grow.

You pay AgentMeter for cost infrastructure. Your customers pay you for what they use through your billing flow.

Free

$0/moUSD
  • - 1 workspace
  • - Up to 100k events / mo
  • - Basic dashboards
  • - Community support
Start free

Pro

Most popular
$29/moUSD

14-day free trial

  • - Up to 5M events / mo
  • - Reactive rules + alerts
  • - Webhooks
  • - Email support
Start Pro trial

Scale

$99/moUSD

14-day free trial

  • - Up to 50M events / mo
  • - Customer billing portal
  • - Advanced rules engine
  • - Priority support
Start Scale trial
FAQ

Frequently asked

How does AgentMeter integrate with my agent?

Install the TypeScript or Python SDK, create a telemetry API key, and send cost-shaped events from your runtime. SDK failures are handled so your host agent does not fail because AgentMeter is unavailable.

Do you read my prompts or completions?

No. AgentMeter expects cost-shaped telemetry only: model, tokens, step name, customer ID, and configured usage metrics. Do not send prompts, completions, emails, or raw user messages.

Can I bill my customers through AgentMeter?

Yes. Stripe Connect, invoice drafts, and the customer portal are part of the billing surface for builders who want customer-facing usage and billing workflows.

What about non-LLM costs?

Use reportUsage / report_usage to track API calls, lookups, executions, or any custom metric. Non-LLM sources can be priced and shown alongside model costs.

Can I self-host it?

The SDKs and core backend are MIT licensed. Enterprise-only modules live under src/ee and are licensed under ELv2.

Get started

Your customers' costs are streaming somewhere.
Make them visible.

Five minutes with the SDK. A real cost picture once events arrive.